数据初识

import pandas as pd
stations = pd.read_csv('stations.csv',encoding='utf-8')
print(stations.head())
#     id     name   lat  long  docks        city
# 0  1.0  '#SAN#'  37.3  -121   27.0  'San Jose'
# 1  1.0  '#SAN#'  37.3  -121   27.0  'San Jose'
# 2  1.0  '#SAN#'  37.3  -121   27.0  'San Jose'
# 3  1.0  '#SAN#'  37.3  -121   27.0  'San Jose'
# 4  1.0  '#SAN#'  37.3  -121   27.0  'San Jose'

trips1 = pd.read_csv('trips1.csv',encoding='utf-8')
print(trips1.shape)
# (6, 5)

trips2 = pd.read_csv('trips2.csv',encoding='utf-8')
print(trips1.shape)
# (6, 5)

trips3 = pd.read_csv('trips3.csv',encoding='utf-8')
print(trips1.shape)
# (6, 5)

#将trips1、trips2、trips3合并为一个Dataframe,命名为trips
trips = pd.concat([trips1,trips2,trips3])
# print(trips.shape)
# (18, 5)

#将stations中所有列名称前添加字段‘start_’,并将start_id设置为列索引
stations.columns = stations.columns.map(lambda x:'start_'+x)
#inplace为true时，对原数据进行修改
# stations.set_index(['start_id'],inplace=True)
print('stations----')
print(stations)


print('-----trips-----')
print(trips)
#将trips和stations按照起始车站id进行字段匹配并合并，保留所有匹配成功的信息
print('----合并后----')
trips_stations = trips.merge(stations,on='start_id'))
print(trips_stations)

#将trips_stations导出为'将'trips_stations.csv'文件

trips_stations.to_csv('trips_stations.csv')